# The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers under Fully Homomorphic Encryption on the Torus

arXiv: https://arxiv.org/abs/2310.02041 · HTML: https://mlsanity.com/paper/2310.02041/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 3 Oct 2023.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [AutoFormer: Searching Transformers for Visual Recognition](https://mlsanity.com/paper/2107.00651/) (2021)
- [Fastformer: Additive Attention Can Be All You Need](https://mlsanity.com/paper/2108.09084/) (2021)
- [A Study on ReLU and Softmax in Transformer](https://mlsanity.com/paper/2302.06461/) (2023)
- [SHE: A Fast and Accurate Deep Neural Network for Encrypted Data](https://mlsanity.com/paper/1906.00148/) (2019)
- [Cryptotree: fast and accurate predictions on encrypted structured data](https://mlsanity.com/paper/2006.08299/) (2020)
- [Inhibitor Transformers and Gated RNNs for Torus Efficient Fully Homomorphic Encryption](https://mlsanity.com/paper/2308.05629/) (2023)

## Abstract (arXiv)

To enhance the computational efficiency of quantized Transformers, we replace the dot-product and Softmax-based attention with an alternative mechanism involving addition and ReLU activation only. This side-steps the expansion to double precision often required by matrix multiplication and avoids costly Softmax evaluations but maintains much of the core functionality of conventional dot-product attention. It can enable more efficient execution and support larger quantized Transformer models on resource-constrained hardware or alternative arithmetic systems like homomorphic encryption. Training experiments on four common benchmark tasks show test set prediction scores comparable to those of conventional Transformers with dot-product attention. Our scaling experiments also suggest significant computational savings, both in plaintext and under encryption. In particular, we believe that the ReLU and addition-based attention mechanism examined in this paper may enable privacy-preserving AI applications operating under homomorphic encryption by avoiding the costly multiplication of encrypted variables.